Lightweight numerical bandits on text embeddings match or exceed LLM accuracy in contextual bandits at a fraction of the cost, with an embedding-based diagnostic to choose between them.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 2roles
background 1polarities
unclear 1representative citing papers
PRISM shows that prompt engineering and selective ICL often outperform complex multi-agent systems on financial retrieval benchmarks while remaining training-free and achieving competitive NDCG@5 scores.
citing papers explorer
-
When Do We Need LLMs? A Diagnostic for Language-Driven Bandits
Lightweight numerical bandits on text embeddings match or exceed LLM accuracy in contextual bandits at a fraction of the cost, with an embedding-based diagnostic to choose between them.
-
PRISM: Prompt-Refined In-Context System Modelling for Financial Retrieval
PRISM shows that prompt engineering and selective ICL often outperform complex multi-agent systems on financial retrieval benchmarks while remaining training-free and achieving competitive NDCG@5 scores.